Quick Start - AgentBasis

5 minutes to get up and running. Just 3 lines of code to start tracking.

Follow these steps to integrate AgentBasis into your application.

1. Install the SDK

pip install agentbasis

2. Get Your Credentials

You’ll need two things from the AgentBasis dashboard:

API Key

Go to Dashboard → Settings → API Keys and copy your API key.

Agent ID

Go to Dashboard → Agents and create a new agent (or select an existing one) to get the Agent ID.

3. Set Environment Variables

Add your credentials to your environment. The SDK will read them automatically.

.env file
Linux / macOS
Windows (PowerShell)

# .env
AGENTBASIS_API_KEY=your-api-key
AGENTBASIS_AGENT_ID=your-agent-id

Load with python-dotenv or your framework’s env loader.

export AGENTBASIS_API_KEY="your-api-key"
export AGENTBASIS_AGENT_ID="your-agent-id"

$env:AGENTBASIS_API_KEY="your-api-key"
$env:AGENTBASIS_AGENT_ID="your-agent-id"

4. Initialize the SDK

Add this at the top of your main application file:

import agentbasis

# Reads from AGENTBASIS_API_KEY and AGENTBASIS_AGENT_ID env vars
agentbasis.init()

Alternative: Pass credentials directly (not recommended for production)

For quick testing, you can pass credentials directly:

agentbasis.init(
    api_key="your-api-key-here", 
    agent_id="your-agent-id-here"
)

Never commit API keys to version control. Use environment variables in production.

5. Instrument Your LLM

Choose your LLM provider and add one line to start tracking:

OpenAI
Anthropic
Gemini

from agentbasis.llms.openai import instrument
instrument()

# Use OpenAI as normal - all calls are now tracked
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello"}]
)

from agentbasis.llms.anthropic import instrument
instrument()

# Use Anthropic as normal
from anthropic import Anthropic
client = Anthropic()
response = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)

from agentbasis.llms.gemini import instrument
instrument()

# Use Gemini as normal
import google.generativeai as genai
model = genai.GenerativeModel("gemini-pro")
response = model.generate_content("Hello")

6. Track Custom Functions (Optional)

Use the @trace decorator to track any function:

from agentbasis import trace

@trace
def process_user_request(query):
    # Your logic here
    return result

What’s Next?

Core Concepts

Learn about context, sessions, and manual tracing

LangChain

Trace chains, agents, and tools

Pydantic AI

Monitor Pydantic AI agents

API Reference

Complete function reference

​1. Install the SDK

​2. Get Your Credentials

​3. Set Environment Variables

​4. Initialize the SDK

​5. Instrument Your LLM

​6. Track Custom Functions (Optional)

​What’s Next?

Core Concepts

LangChain

Pydantic AI

API Reference

1. Install the SDK

2. Get Your Credentials

3. Set Environment Variables

4. Initialize the SDK

5. Instrument Your LLM

6. Track Custom Functions (Optional)

What’s Next?